Extracting and Learning an Unknown Grammar with Recurrent Neural Networks
Giles, C. L., Miller, C. B., Chen, D., Sun, G. Z., Chen, H. H., Lee, Y. C.
–Neural Information Processing Systems
We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning (RTRL) method that computes the complete gradient and updates the weights at the end of each string.
Neural Information Processing Systems
Dec-31-1992
- Country:
- North America > United States
- Maryland (0.04)
- District of Columbia > Washington (0.04)
- New Jersey > Mercer County
- Princeton (0.04)
- Massachusetts > Middlesex County
- Reading (0.04)
- California > San Mateo County
- San Mateo (0.04)
- Redwood City (0.04)
- North America > United States
- Technology: